Sparse-autoencoder features from LLMs trigger automatic prompt reformulation, yielding consistent gains on mathematical reasoning and metaphor detection.
FrameBERT: Conceptual Metaphor Detection with Frame Embedding Learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
In this paper, we propose FrameBERT, a RoBERTa-based model that can explicitly learn and incorporate FrameNet Embeddings for concept-level metaphor detection. FrameBERT not only achieves better or comparable performance to the state-of-the-art, but also is more explainable and interpretable compared to existing models, attributing to its ability of accounting for external knowledge of FrameNet.
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Exploring Task Performance with Interpretable Models via Sparse Auto-Encoders
Sparse-autoencoder features from LLMs trigger automatic prompt reformulation, yielding consistent gains on mathematical reasoning and metaphor detection.